The anti‐oxidation mechanism of SiCf/SiC–B4C modified with Al2O3 in wet atmosphere based on machine learning

Shan, Qingliang; Xue, Yudong; Hu, Jianbao

doi:10.1111/jace.18525

Cited by 7 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the same damage mode will produce the similar AE feature values, while different damage modes will produce different AE feature value. The AE feature values (i.e., count ( C ), rise‐time ( R_T ), Energy ( E ), duration ( D ), peak frequency ( P_F ), amplitude ( A ), decay time ( D_T ), and absolute energy ( A_E )) obtained from the bending tests are handled with ML technique for better distinguishing different damage modes 22 . The main process are as follows: (1) Uncorrelated AE features selection: Since every AE signal obtained from three‐point bending test of AT‐FC is consisted of many AE feature values, it is necessary to eliminate high correlation AE features before clustering.…”

Section: Methodsmentioning

confidence: 99%

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Shan

Qian

Xue

et al. 2023

Int J Applied Ceramic Tech

Self Cite

View full text Add to dashboard Cite

The damage modes of Al2TiO5 flexible ceramics (AT) with microcracks strengthened were studied by machine leaning for damage mode identification. Results show that the optimal number of clusters increases from 3 to 4 with the increase of ZrO2 content. Meanwhile, the concentrated region of cluster with the same label gradually shifts to the direction of low amplitude with increase of ZrO2. In addition, the quantity of cluster is easy saturated since the AT grain boundary microcracks are strengthened by the formation of ZrTiO4. For achieving the automatic identification of different damage modes, support vector machine based on Kennard‐stone training set selection was used to distinguish the damage modes of other samples in the same sample set. Almost the same evolution trend of corresponding clusters in new samples and training samples proves high efficiencies of this method.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Shan

Qian

Xue

et al. 2023

Int J Applied Ceramic Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…Further details on the composites preparation process, mechanical test process, and machine learning processing method can be viewed in refs. 18, 19. In this study, the virgin composite samples before oxidation, after oxidation for 50 h, and after oxidation for 100 h are labeled as virgin‐0 h, virgin‐50 h, and virgin‐100 h, respectively.…”

Section: Experimental Processmentioning

confidence: 99%

Initial damage behavior of Al₂O₃‐modified SiC_f/SiC–B₄C composites after oxidation under wet atmosphere at 1200°C

Shan,

Tian,

Xue

et al. 2024

J Am Ceram Soc.

Self Cite

View full text Add to dashboard Cite

Al2O3 was incorporated into SiCf/SiC–B4C composites to improve their mechanical properties after oxidation. The results showed that Al2O3 reduced the weight gain of these composites, and the oxidized layer became smooth and dense. The fibers pull‐out lengths of the Al2O3‐modified composites were longer than that of virgin composites oxidized for the same amount of time. Compared with the virgin composites, the tensile strength retention rate of Al2O3‐modified composites was improved by 7.3% and 8.4% after oxidation times of 50 and 100 h, respectively. But Al2O3 modification led to 20.6% and 44.3% improvements in σonset (acoustic emission, AE onset stress) as well as 76.5% and 95.5% the improvements in σmin (first AE stress), respectively. Further investigation indicated that a higher proportion of high‐energy level events occurred in the Al2O3‐modified composites when the load just reached the damage thresholds stress compared with the virgin composites.

show abstract

“…Acoustic emission (AE) is widely used in real-time monitoring the damage process in materials. [6][7][8][9][10][11][12][13][14][15] Generally, the gathered AE data will be saved as the signal parameters such as energy, count, rise time, duration, and amplitude. These key parameters can be utilized directly or as a derived combinations.…”

mentioning

confidence: 99%

The Damage Mode Automatic Identification of Al₂TiO₅ Flexible Ceramics Based on Machine Learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

Al 2 TiO 5 flexible ceramics (AT-FCs) are attractive material with nonlinear stress-strain behavior due to their multi-cracks structure. [1,2] The application of AT-FC to prepare shockproof component especially in high temperature has emerged as a new and viable choice. Although researches toward enhancing the study of AT-FC have been going on for more than 10 years, the damage-mode evolution inside still remains elusive. [3][4][5] Using nondestructive techniques will increase the confidence of both engineers and researchers in the full utilization of the potential of this material. Acoustic emission (AE) is widely used in real-time monitoring the damage process in materials. [6][7][8][9][10][11][12][13][14][15] Generally, the gathered AE data will be saved as the signal parameters such as energy, count, rise time, duration, and amplitude. These key parameters can be utilized directly or as a derived combinations. [11] In AT-FC, the possible AE single source mainly results from the fracture of grain boundary glass phase, friction between grains, and grains failure. [16] Meanwhile, a single-damage mode, such as fracture of grain boundary glass phase, can provide multiple AE signal parameters. In addition, the overlapping of AE parameters distribution area is ineluctable due to the equipment settings, dense AE from various signal sources, and signal fading. [11,17] Therefore, the relationship between each damage mode of AT-FC and AE signal parameters has not been built. However, to achieve damage-mode automatic identification of AT-FC, it is necessary to build this relationship in advance. Machine learning (ML) is a suitable method for accomplishing the corresponding relationship between each damage mode of AT-FC and AE signal parameters to realize automatic identification of damage mode. The ML algorithms contain two modes, unsupervised and supervised. [18] The target of unsupervised ML is to classify the AE parameters with similar characteristics into groups and utilize those groups to distinguish different damage modes, while supervised ML is used to identify the damage modes of other materials in the same set using the distinguished damage modes.Generally, the AE signals handled by ML algorithms have been concentrated on the mechanical properties analysis of fiber-reinforced ceramic/glass matrix composites. Moevus et al. [19] employed the unsupervised ML algorithms, k-means, to explore the damage modes of two kinds of SiC f /[Si-B-C] composites. Five and four damage modes were accurately distinguished in elongation composites and stiff composites, respectively. Meanwhile, Kostopoulos et al. [13] successfully identified three damage modes in SiC/mixed abrasive slurry-L (ceramic glass matrix) composites utilizing k-means algorithms. However, it is necessary to combine the unsupervised ML algorithms with supervised ML algorithms to achieve the automatic identification

show abstract

The anti‐oxidation mechanism of SiC_f/SiC–B₄C modified with Al₂O₃ in wet atmosphere based on machine learning

Cited by 7 publications

References 27 publications

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Initial damage behavior of Al₂O₃‐modified SiC_f/SiC–B₄C composites after oxidation under wet atmosphere at 1200°C

The Damage Mode Automatic Identification of Al₂TiO₅ Flexible Ceramics Based on Machine Learning

Contact Info

Product

Resources

About

The anti‐oxidation mechanism of SiCf/SiC–B4C modified with Al2O3 in wet atmosphere based on machine learning

Cited by 7 publications

References 27 publications

Machine learning in Al2TiO5 flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Machine learning in Al2TiO5 flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Initial damage behavior of Al2O3‐modified SiCf/SiC–B4C composites after oxidation under wet atmosphere at 1200°C

The Damage Mode Automatic Identification of Al2TiO5 Flexible Ceramics Based on Machine Learning

Contact Info

Product

Resources

About

The anti‐oxidation mechanism of SiC_f/SiC–B₄C modified with Al₂O₃ in wet atmosphere based on machine learning

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Machine learning in Al₂TiO₅ flexible ceramics with microcrcaks strengthened for damage mode automatic identification

Initial damage behavior of Al₂O₃‐modified SiC_f/SiC–B₄C composites after oxidation under wet atmosphere at 1200°C

The Damage Mode Automatic Identification of Al₂TiO₅ Flexible Ceramics Based on Machine Learning